feat(ai-analyze): 新增 Markdown 文件 AI 分析功能
- 添加 Markdown 文件上传和解析接口 - 实现流式分析和大纲提取功能 - 支持多种分析类型：摘要、大纲、关键点等 - 新增 markdown_ai_service 服务类 - 扩展 LLMService 支持流式调用 - 更新前端 API 接口定义和实现
This commit is contained in:
@@ -2,10 +2,14 @@
|
||||
AI 分析 API 接口
|
||||
"""
|
||||
from fastapi import APIRouter, UploadFile, File, HTTPException, Query, Body
|
||||
from fastapi.responses import StreamingResponse
|
||||
from typing import Optional
|
||||
import logging
|
||||
import tempfile
|
||||
import os
|
||||
|
||||
from app.services.excel_ai_service import excel_ai_service
|
||||
from app.services.markdown_ai_service import markdown_ai_service
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -93,10 +97,11 @@ async def get_analysis_types():
|
||||
获取支持的分析类型列表
|
||||
|
||||
Returns:
|
||||
list: 支持的分析类型
|
||||
dict: 支持的分析类型（包含 Excel 和 Markdown）
|
||||
"""
|
||||
return {
|
||||
"types": excel_ai_service.get_supported_analysis_types()
|
||||
"excel_types": excel_ai_service.get_supported_analysis_types(),
|
||||
"markdown_types": markdown_ai_service.get_supported_analysis_types()
|
||||
}
|
||||
|
||||
|
||||
@@ -142,3 +147,185 @@ async def analyze_text(
|
||||
except Exception as e:
|
||||
logger.error(f"文本分析失败: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=f"分析失败: {str(e)}")
|
||||
|
||||
|
||||
@router.post("/analyze/md")
|
||||
async def analyze_markdown(
|
||||
file: UploadFile = File(...),
|
||||
analysis_type: str = Query("summary", description="分析类型: summary, outline, key_points, questions, tags, qa, statistics, section"),
|
||||
user_prompt: str = Query("", description="用户自定义提示词"),
|
||||
section_number: Optional[str] = Query(None, description="指定章节编号，如 '一' 或 '（一）'")
|
||||
):
|
||||
"""
|
||||
上传并使用 AI 分析 Markdown 文件
|
||||
|
||||
Args:
|
||||
file: 上传的 Markdown 文件
|
||||
analysis_type: 分析类型
|
||||
user_prompt: 用户自定义提示词
|
||||
section_number: 指定分析的章节编号
|
||||
|
||||
Returns:
|
||||
dict: 分析结果
|
||||
"""
|
||||
# 检查文件类型
|
||||
if not file.filename:
|
||||
raise HTTPException(status_code=400, detail="文件名为空")
|
||||
|
||||
file_ext = file.filename.split('.')[-1].lower()
|
||||
if file_ext not in ['md', 'markdown']:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"不支持的文件类型: {file_ext}，仅支持 .md 和 .markdown"
|
||||
)
|
||||
|
||||
# 验证分析类型
|
||||
supported_types = markdown_ai_service.get_supported_analysis_types()
|
||||
if analysis_type not in supported_types:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"不支持的分析类型: {analysis_type}，支持的类型: {', '.join(supported_types)}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 读取文件内容
|
||||
content = await file.read()
|
||||
|
||||
# 保存到临时文件
|
||||
with tempfile.NamedTemporaryFile(mode='wb', suffix='.md', delete=False) as tmp:
|
||||
tmp.write(content)
|
||||
tmp_path = tmp.name
|
||||
|
||||
try:
|
||||
logger.info(f"开始分析 Markdown 文件: {file.filename}, 分析类型: {analysis_type}, 章节: {section_number}")
|
||||
|
||||
# 调用 AI 分析服务
|
||||
result = await markdown_ai_service.analyze_markdown(
|
||||
file_path=tmp_path,
|
||||
analysis_type=analysis_type,
|
||||
user_prompt=user_prompt,
|
||||
section_number=section_number
|
||||
)
|
||||
|
||||
logger.info(f"Markdown 分析完成: {file.filename}, 成功: {result['success']}")
|
||||
|
||||
if not result['success']:
|
||||
raise HTTPException(status_code=500, detail=result.get('error', '分析失败'))
|
||||
|
||||
return result
|
||||
|
||||
finally:
|
||||
# 清理临时文件
|
||||
if os.path.exists(tmp_path):
|
||||
os.unlink(tmp_path)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Markdown AI 分析过程中出错: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=f"分析失败: {str(e)}")
|
||||
|
||||
|
||||
@router.post("/analyze/md/stream")
|
||||
async def analyze_markdown_stream(
|
||||
file: UploadFile = File(...),
|
||||
analysis_type: str = Query("summary", description="分析类型"),
|
||||
user_prompt: str = Query("", description="用户自定义提示词"),
|
||||
section_number: Optional[str] = Query(None, description="指定章节编号")
|
||||
):
|
||||
"""
|
||||
流式分析 Markdown 文件 (SSE)
|
||||
|
||||
Returns:
|
||||
StreamingResponse: SSE 流式响应
|
||||
"""
|
||||
if not file.filename:
|
||||
raise HTTPException(status_code=400, detail="文件名为空")
|
||||
|
||||
file_ext = file.filename.split('.')[-1].lower()
|
||||
if file_ext not in ['md', 'markdown']:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"不支持的文件类型: {file_ext}，仅支持 .md 和 .markdown"
|
||||
)
|
||||
|
||||
try:
|
||||
content = await file.read()
|
||||
|
||||
with tempfile.NamedTemporaryFile(mode='wb', suffix='.md', delete=False) as tmp:
|
||||
tmp.write(content)
|
||||
tmp_path = tmp.name
|
||||
|
||||
try:
|
||||
logger.info(f"开始流式分析 Markdown 文件: {file.filename}, 分析类型: {analysis_type}")
|
||||
|
||||
async def stream_generator():
|
||||
async for chunk in markdown_ai_service.analyze_markdown_stream(
|
||||
file_path=tmp_path,
|
||||
analysis_type=analysis_type,
|
||||
user_prompt=user_prompt,
|
||||
section_number=section_number
|
||||
):
|
||||
yield chunk
|
||||
|
||||
return StreamingResponse(
|
||||
stream_generator(),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive",
|
||||
"X-Accel-Buffering": "no"
|
||||
}
|
||||
)
|
||||
|
||||
finally:
|
||||
if os.path.exists(tmp_path):
|
||||
os.unlink(tmp_path)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Markdown AI 流式分析出错: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=f"流式分析失败: {str(e)}")
|
||||
|
||||
|
||||
@router.get("/analyze/md/outline")
|
||||
async def get_markdown_outline(
|
||||
file: UploadFile = File(...)
|
||||
):
|
||||
"""
|
||||
获取 Markdown 文档的大纲结构（分章节信息）
|
||||
|
||||
Args:
|
||||
file: 上传的 Markdown 文件
|
||||
|
||||
Returns:
|
||||
dict: 文档大纲结构
|
||||
"""
|
||||
if not file.filename:
|
||||
raise HTTPException(status_code=400, detail="文件名为空")
|
||||
|
||||
file_ext = file.filename.split('.')[-1].lower()
|
||||
if file_ext not in ['md', 'markdown']:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"不支持的文件类型: {file_ext}，仅支持 .md 和 .markdown"
|
||||
)
|
||||
|
||||
try:
|
||||
content = await file.read()
|
||||
|
||||
with tempfile.NamedTemporaryFile(mode='wb', suffix='.md', delete=False) as tmp:
|
||||
tmp.write(content)
|
||||
tmp_path = tmp.name
|
||||
|
||||
try:
|
||||
result = await markdown_ai_service.extract_outline(tmp_path)
|
||||
return result
|
||||
finally:
|
||||
if os.path.exists(tmp_path):
|
||||
os.unlink(tmp_path)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"获取 Markdown 大纲失败: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=f"获取大纲失败: {str(e)}")
|
||||
|
||||
Reference in New Issue
Block a user